Source code for segmentation_models_pytorch.decoders.pan.model

from typing import Any, Callable, Literal, Optional, Union
import warnings

from segmentation_models_pytorch.base import (
    ClassificationHead,
    SegmentationHead,
    SegmentationModel,
)
from segmentation_models_pytorch.encoders import get_encoder
from segmentation_models_pytorch.base.hub_mixin import supports_config_loading

from .decoder import PANDecoder


[docs] class PAN(SegmentationModel): """Implementation of PAN_ (Pyramid Attention Network). Note: Currently works with shape of input tensor >= [B x C x 128 x 128] for pytorch <= 1.1.0 and with shape of input tensor >= [B x C x 256 x 256] for pytorch == 1.3.1 Args: encoder_name: Name of the classification model that will be used as an encoder (a.k.a backbone) to extract features of different spatial resolution encoder_depth: A number of stages used in encoder in range [3, 5]. Each stage generate features two times smaller in spatial dimensions than previous one (e.g. for depth 0 we will have features with shapes [(N, C, H, W),], for depth 1 - [(N, C, H, W), (N, C, H // 2, W // 2)] and so on). Default is 5 encoder_weights: One of **None** (random initialization), **"imagenet"** (pre-training on ImageNet) and other pretrained weights (see table with available weights for each encoder_name) encoder_output_stride: 16 or 32, if 16 use dilation in encoder last layer. Doesn't work with ***ception***, **vgg***, **densenet*`** backbones.Default is 16. decoder_channels: A number of convolution layer filters in decoder blocks decoder_interpolation: Interpolation mode used in decoder of the model. Available options are **"nearest"**, **"bilinear"**, **"bicubic"**, **"area"**, **"nearest-exact"**. Default is **"bilinear"**. in_channels: A number of input channels for the model, default is 3 (RGB images) classes: A number of classes for output mask (or you can think as a number of channels of output mask) activation: An activation function to apply after the final convolution layer. Available options are **"sigmoid"**, **"softmax"**, **"logsoftmax"**, **"tanh"**, **"identity"**, **callable** and **None**. Default is **None**. upsampling: Final upsampling factor. Default is 4 to preserve input-output spatial shape identity aux_params: Dictionary with parameters of the auxiliary output (classification head). Auxiliary output is build on top of encoder if **aux_params** is not **None** (default). Supported params: - classes (int): A number of classes - pooling (str): One of "max", "avg". Default is "avg" - dropout (float): Dropout factor in [0, 1) - activation (str): An activation function to apply "sigmoid"/"softmax" (could be **None** to return logits) kwargs: Arguments passed to the encoder class ``__init__()`` function. Applies only to ``timm`` models. Keys with ``None`` values are pruned before passing. Returns: ``torch.nn.Module``: **PAN** .. _PAN: https://arxiv.org/abs/1805.10180 """ @supports_config_loading def __init__( self, encoder_name: str = "resnet34", encoder_depth: Literal[3, 4, 5] = 5, encoder_weights: Optional[str] = "imagenet", encoder_output_stride: Literal[16, 32] = 16, decoder_channels: int = 32, decoder_interpolation: str = "bilinear", in_channels: int = 3, classes: int = 1, activation: Optional[Union[str, Callable]] = None, upsampling: int = 4, aux_params: Optional[dict] = None, **kwargs: dict[str, Any], ): super().__init__() if encoder_output_stride not in [16, 32]: raise ValueError( "PAN support output stride 16 or 32, got {}".format( encoder_output_stride ) ) upscale_mode = kwargs.pop("upscale_mode", None) if upscale_mode is not None: warnings.warn( "The usage of upscale_mode is deprecated. Please modify your code for decoder_interpolation", DeprecationWarning, stacklevel=2, ) decoder_interpolation = upscale_mode self.encoder = get_encoder( encoder_name, in_channels=in_channels, depth=encoder_depth, weights=encoder_weights, output_stride=encoder_output_stride, **kwargs, ) self.decoder = PANDecoder( encoder_channels=self.encoder.out_channels, encoder_depth=encoder_depth, decoder_channels=decoder_channels, interpolation_mode=decoder_interpolation, ) self.segmentation_head = SegmentationHead( in_channels=decoder_channels, out_channels=classes, activation=activation, kernel_size=3, upsampling=upsampling, ) if aux_params is not None: self.classification_head = ClassificationHead( in_channels=self.encoder.out_channels[-1], **aux_params ) else: self.classification_head = None self.name = "pan-{}".format(encoder_name) self.initialize()